Maintaining Symmetry between Convolutional Neural Network Accuracy and Performance on an Edge TPU with a Focus on Transfer Learning Adjustments

C DeLozier, J Blanco, R Rakvic, J Shey - Symmetry, 2024 - mdpi.com
Transfer learning has proven to be a valuable technique for deploying machine learning
models on edge devices and embedded systems. By leveraging pre-trained models and fine …

Output-directed dynamic quantization for DNN acceleration

B Jiang, X Cheng, Y Li, J Zhang, S Fu, Q Yang… - Proceedings of the …, 2023 - dl.acm.org
Quantization is an effective technique for reducing the number of computations and
improving the performance of deep neural networks (DNNs). Weight quantization is popular …